Arker vs TenkiSandbox Benchmark Comparison

Arker
Faster in 1 of 2
vs
Tenki
Faster in 1 of 2

Arker and Tenki were each faster in 1 of 2 shared sandbox benchmarks.

Shared benchmarks
2
Last run
October 30, 2026
Want the full run details?Sign up free →

Scorecard

Median of each benchmark's primary metric; lower is better. Medians within 5% count as roughly even, and a benchmark gets no speed verdict when either provider completed fewer than 50% of runs.

BenchmarkArkerTenkiResultRatio
Burst TTI
Time to interactive · Run October 30, 2026
324ms
100% success
2.10s
100% success
Arker faster
6.49x
DAX
Total workload time · Run October 30, 2026
64.68s
100% success
60.78s
100% success
Tenki faster
1.06x

Burst TTI

Run October 30, 2026

Time from sandbox creation to the first successful command, with 100 sandboxes launched at the same time.

Time to interactive

Arker

100% success
Median
324ms
P95
394ms
P99
403ms
Arker Burst TTI results →

Tenki

100% success
Median
2.10s
P95
2.18s
P99
2.18s
Tenki Burst TTI results →

Arker had a 6.49x lower median time to interactive (324ms vs 2.10s for Tenki).

Median time to interactive over time

16 runs from August 7, 2026 to October 30, 2026.

ArkerTenki
View the full Burst TTI leaderboard →

DAX

Run October 30, 2026

A real developer workload: install system packages, download Bun, clone the opencode repo, then run bun install and bun typecheck.

Total workload time

Arker

100% success
Median
64.68s
P95
64.68s
P99
64.68s
Arker DAX results →

Tenki

100% success
Median
60.78s
P95
60.78s
P99
60.78s
Tenki DAX results →

Tenki had a 1.06x lower median total workload time (60.78s vs 64.68s for Arker).

Median total workload time over time

15 runs from August 7, 2026 to October 30, 2026.

ArkerTenki
View the full DAX leaderboard →

Methodology

  • One workload, every provider. The same script, payload, and model hit every provider, addressed the way its own API expects. Nobody gets a tuned or special path.
  • Repeated on a schedule. Every suite runs many iterations per provider, automated on a recurring schedule, so results reflect steady state rather than one lucky request.
  • Raw results published. Every run is committed as JSON to the public benchmarks repo, next to the code that produced it. Nothing is cherry-picked or held back.
  • How this comparison is built. Each benchmark compares the two providers' medians; results within 5% count as roughly even. A comparison is published only when both providers completed at least 50% of runs in 2 or more shared benchmarks run in the last 30 days.

Frequently asked questions

Have another question? Email us.

Arker and Tenki were each faster in 1 of 2 shared sandbox benchmarks. In Burst TTI (October 30, 2026), Arker had a median time to interactive of 324ms versus 2.10s for Tenki, 6.49x faster. In DAX (October 30, 2026), Tenki had a median total workload time of 60.78s versus 64.68s for Arker, 1.06x faster.

PartnersGoogle Cloud Run